Skip to content
Navigation menu
Search
Powered by Algolia
Search
Log in
Create account
Forem
Close
#
llm
Follow
Hide
Posts
Left menu
đź‘‹
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
Right menu
Claude Went Down Twice in 48 Hours Last Week. If You Noticed, Your Fallback Failed.
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
Apr 18
Claude Went Down Twice in 48 Hours Last Week. If You Noticed, Your Fallback Failed.
#
ai
#
devops
#
llm
#
observability
Comments
Add Comment
8 min read
Part 4 of 4 — Engineering Intent Series : ISL v1.6.2: Evolution for Complex Systems
Francesco Marconi
Francesco Marconi
Francesco Marconi
Follow
Apr 18
Part 4 of 4 — Engineering Intent Series : ISL v1.6.2: Evolution for Complex Systems
#
ai
#
llm
#
programming
#
productivity
Comments
Add Comment
6 min read
Cursor 3 Just Shipped a Coding Model Trained From Scratch. Here's Why That Changes the Stack.
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
Apr 18
Cursor 3 Just Shipped a Coding Model Trained From Scratch. Here's Why That Changes the Stack.
#
ai
#
webdev
#
productivity
#
llm
Comments
Add Comment
8 min read
A $10B AI Startup Just Got Breached Through the LLM Library in Your Stack.
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
Apr 18
A $10B AI Startup Just Got Breached Through the LLM Library in Your Stack.
#
ai
#
security
#
llm
#
devops
Comments
Add Comment
8 min read
Why Your LangChain Agent Keeps Calling the Same Tool in a Loop (and How to Stop It)
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
Apr 18
Why Your LangChain Agent Keeps Calling the Same Tool in a Loop (and How to Stop It)
#
ai
#
llm
#
python
#
webdev
Comments
Add Comment
7 min read
8 Ways Your LLM App Is Silently Failing Right Now (and What to Instrument for Each)
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
Apr 18
8 Ways Your LLM App Is Silently Failing Right Now (and What to Instrument for Each)
#
ai
#
observability
#
llm
#
devops
Comments
Add Comment
6 min read
Datadog Sees the HTTP 200. It Cannot See the Hallucination.
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
Apr 18
Datadog Sees the HTTP 200. It Cannot See the Hallucination.
#
ai
#
observability
#
llm
#
devops
Comments
Add Comment
4 min read
Your First AI Agent in 50 Lines of Python (No Framework, No LangChain)
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
Apr 18
Your First AI Agent in 50 Lines of Python (No Framework, No LangChain)
#
ai
#
python
#
llm
#
beginners
Comments
Add Comment
7 min read
OpenTelemetry GenAI Semantic Conventions: Your LLM Traces Should Look Like This in 2026
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
Apr 18
OpenTelemetry GenAI Semantic Conventions: Your LLM Traces Should Look Like This in 2026
#
ai
#
observability
#
opentelemetry
#
llm
Comments
Add Comment
5 min read
RAG Is Dead. Long Live RAG.
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
Apr 18
RAG Is Dead. Long Live RAG.
#
ai
#
llm
#
rag
#
webdev
Comments
Add Comment
11 min read
The 5 RAG Failure Modes Nobody Talks About (and How to Detect Them Before Users Do)
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
Apr 18
The 5 RAG Failure Modes Nobody Talks About (and How to Detect Them Before Users Do)
#
ai
#
llm
#
rag
#
observability
Comments
Add Comment
8 min read
Langfuse vs LangSmith vs Phoenix vs Braintrust: The Honest 2026 Comparison
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
Apr 18
Langfuse vs LangSmith vs Phoenix vs Braintrust: The Honest 2026 Comparison
#
ai
#
observability
#
llm
#
devops
Comments
Add Comment
5 min read
The Production Readiness Checklist for LLM Apps Nobody Gave You (18 Items)
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
Apr 18
The Production Readiness Checklist for LLM Apps Nobody Gave You (18 Items)
#
ai
#
observability
#
llm
#
devops
Comments
Add Comment
5 min read
I Built an AI Agent That Fired Itself After 3 Minutes. Here's Why That's a Feature.
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
Apr 18
I Built an AI Agent That Fired Itself After 3 Minutes. Here's Why That's a Feature.
#
ai
#
llm
#
python
#
webdev
Comments
Add Comment
7 min read
LLM-as-Judge: The Eval Technique That Looks Cheap Until It Grades Its Own Bias Back to You
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
Apr 18
LLM-as-Judge: The Eval Technique That Looks Cheap Until It Grades Its Own Bias Back to You
#
ai
#
testing
#
llm
#
observability
Comments
Add Comment
7 min read
đź‘‹
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
We're a blogging-forward open source social network where we learn from one another
Log in
Create account